publications

2026

1. RLC

   

   Learning Communication Skills in Multi-task Multi-agent Deep Reinforcement Learning

   Changxi Zhu, Mehdi Dastani, Shihan Wang

   Reinforcement Learning Conference (RLC)

   Bib PDF Website

   @inproceedings{Zhu2026MCS,
                         title={Learning Communication Skills in Multi-task Multi-agent Deep Reinforcement Learning},
                         author={Zhu, Changxi and Dastani, Mehdi and Wang, Shihan},
                         booktitle={Reinforcement Learning Conference (RLC)},
                         eprint={2511.03348},
                         archivePrefix={arXiv},
                         year={2026}}
                       

2025

1. arXiv

   

   Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning

   Changxi Zhu, Mehdi Dastani, and Shihan Wang

   2025

   Bib PDF

   @article{Zhu2025Reducing,
                     title={Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning},
                     author={Zhu, Changxi and Dastani, Mehdi and Wang, Shihan},
                     journal={arXiv preprint arXiv:2502.06261},
                     year={2025}}

   NCAA

   

   Communication with factorized policy gradients in multi-agent deep reinforcement learning

   Changxi Zhu, Mehdi Dastani, and Shihan Wang

   Neural Computing and Applications

   Bib PDF

   @article{Zhu2025CFPG,
                     title={Communication with factorized policy gradients in multi-agent deep reinforcement learning},
                     author={Zhu, Changxi and Dastani, Mehdi and Wang, Shihan},
                     journal={Neural Computing and Applications},
                     year={2025}}

2024

1. JAAMAS

   

   A survey of multi-agent deep reinforcement learning with communication

   Changxi Zhu, Mehdi Dastani, and Shihan Wang

   Autonomous Agents and Multi-Agent Systems

   Bib PDF

   @article{Zhu2024Survey,
                     title={A survey of multi-agent deep reinforcement learning with communication},
                     author={Zhu, Changxi and Dastani, Mehdi and Wang, Shihan},
                     journal={Autonomous Agents and Multi-Agent Systems},
                     year={2024},
                     publisher={Springer}
                   }